{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/geolrm-geometry-aware-large-reconstruction","title":"GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation","arxiv_id":"2406.15333","date":"2024-06-21","proceeding":null,"authors":["Chubin Zhang","Hongliang Song","Yi Wei","Yu Chen","Jiwen Lu","Yansong Tang"],"abstract":"In this work, we introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. This limits these methods to a low-resolution representation and makes it difficult to scale up to the dense views for better quality. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms to effectively integrate image features into 3D representations. We implement this solution through a two-stage pipeline: initially, a lightweight proposal network generates a sparse set of 3D anchor points from the posed image inputs; subsequently, a specialized reconstruction transformer refines the geometry and retrieves textural details. Extensive experimental results demonstrate that GeoLRM significantly outperforms existing models, especially for dense view inputs. We also demonstrate the practical applicability of our model with 3D generation tasks, showcasing its versatility and potential for broader adoption in real-world applications. The project page: https://linshan-bin.github.io/GeoLRM/.","url_abs":"https://arxiv.org/abs/2406.15333v2","url_pdf":"https://arxiv.org/pdf/2406.15333v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"geolrm-geometry-aware-large-reconstruction","repo_url":"https://github.com/alibaba-yuanjing-aigclab/geolrm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":null,"task_name":"GPU"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.15333","atlas_url":"https://app.syntology.ai/?focus=2406.15333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15333"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba-yuanjing-aigclab/geolrm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":8,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9e6e6de54d3e0f7b","entry":"center_looking_at_camera_pose","repo":"alibaba-yuanjing-aigclab/geolrm","repo_kind":"official","path":"src/utils/camera_util.py","file_url":"https://github.com/alibaba-yuanjing-aigclab/geolrm/blob/HEAD/src/utils/camera_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9e6e6de54d3e0f7b"}},{"code_sha256_prefix":"e4065e60cb9a25bc","entry":"get_batch","repo":"alibaba-yuanjing-aigclab/geolrm","repo_kind":"official","path":"sv3d_video_sample.py","file_url":"https://github.com/alibaba-yuanjing-aigclab/geolrm/blob/HEAD/sv3d_video_sample.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4065e60cb9a25bc"}},{"code_sha256_prefix":"4e24b058c8c88efb","entry":"get_rays","repo":"alibaba-yuanjing-aigclab/geolrm","repo_kind":"official","path":"src/utils/camera_util.py","file_url":"https://github.com/alibaba-yuanjing-aigclab/geolrm/blob/HEAD/src/utils/camera_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4e24b058c8c88efb"}},{"code_sha256_prefix":"da7df331dab819db","entry":"get_unique_embedder_keys_from_conditioner","repo":"alibaba-yuanjing-aigclab/geolrm","repo_kind":"official","path":"sv3d_video_sample.py","file_url":"https://github.com/alibaba-yuanjing-aigclab/geolrm/blob/HEAD/sv3d_video_sample.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da7df331dab819db"}},{"code_sha256_prefix":"dd23b2696bcd01c0","entry":"pad_camera_extrinsics_4x4","repo":"alibaba-yuanjing-aigclab/geolrm","repo_kind":"official","path":"src/utils/camera_util.py","file_url":"https://github.com/alibaba-yuanjing-aigclab/geolrm/blob/HEAD/src/utils/camera_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd23b2696bcd01c0"}},{"code_sha256_prefix":"bd01e0e475e31e12","entry":"read_camera_info_single","repo":"alibaba-yuanjing-aigclab/geolrm","repo_kind":"official","path":"src/datasets/gobjaverse.py","file_url":"https://github.com/alibaba-yuanjing-aigclab/geolrm/blob/HEAD/src/datasets/gobjaverse.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd01e0e475e31e12"}},{"code_sha256_prefix":"dbfd6882e8fac29b","entry":"resize_foreground","repo":"alibaba-yuanjing-aigclab/geolrm","repo_kind":"official","path":"src/utils/infer_util.py","file_url":"https://github.com/alibaba-yuanjing-aigclab/geolrm/blob/HEAD/src/utils/infer_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dbfd6882e8fac29b"}},{"code_sha256_prefix":"ba4e46ed1b9e856c","entry":"unity2blender","repo":"alibaba-yuanjing-aigclab/geolrm","repo_kind":"official","path":"src/datasets/gobjaverse.py","file_url":"https://github.com/alibaba-yuanjing-aigclab/geolrm/blob/HEAD/src/datasets/gobjaverse.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba4e46ed1b9e856c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}